About this role
In 1600, William Gilbert published De Magnete —the first systematic study of magnetism. He didn't just theorize; he built instruments, ran experiments, and shared what he learned so that others could go further. Three centuries later, those foundations helped power the modern world.
At Mercury, we're making a deliberate, company-wide bet on AI. Frontier users are already pushing boundaries—building agents, automating workflows, moving fast. But they're doing it in silos. This role exists to change that: to take those scattered experiments and turn them into shared infrastructure, shared context, and shared capability. The goal is a multiplier effect—where the most ambitious AI work inside Mercury lifts the velocity of everyone else.
What you'll do
You'll join a team that has already started building Mercury's internal AI platform and enablement layer. Your work will be to extend, harden, and scale what's in motion , and to help partner teams adopt it.
Extend the AI platform foundation
• Build and evolve MCP servers that connect internal systems and data sources into a coherent interface for agents and engineers.
• Expand and operate our LLM gateway infrastructure: routing, rate limiting, cost attribution, and observability across teams.
• Turn early patterns into durable defaults: shared prompt libraries, guardrails, and policy-as-code so teams can move fast safely.
Strengthen the shared company knowledge layer
• Shape and maintain structured context artifacts—clean, reliable, agent-consumable—so LLMs working in Mercury's systems can reason accurately about our domain.
• Improve internal knowledge discoverability and retrieval so both humans and agents can quickly find accurate answers.
• Partner with domain teams to standardize key sources of truth, and keep them fresh.
Enable faster prototyping and iteration across the company
• Build and refine sandbox environments and tooling that let engineers experiment with AI safely and at speed.
• Create self-service scaffolding so non-engineers—PMs, ops, finance—can prototype and deploy AI-powered workflows with minimal hand-holding.
• Build playgrounds and evaluation harnesses so internal AI agents can be tested and iterated in controlled environments before hitting production.
This list is illustrative. Priorities will shift as we learn; the right person will help choose the next highest-leverage work.
The ideal candidate
• Has 5+ years of backend development experience in complex, production systems—you've built things that other engineers depended on.
• Is fluent across programming languages and can navigate platform engineering, infrastructure, and developer tooling without needing a map.
• Has hands-on experience building LLM-powered systems—RAG pipelines, agents, eval frameworks—and has shipped at least one of these to production.
• Understands the real tradeoffs in AI deployments: cost modeling, observability, latency, and safety—not just the exciting parts.
• I